vvzvlad/allora
1
0
Fork 0
Code Pull Requests Packages Releases Activity

Compare commits

base: vvzvlad:XGBRegressor-v1
Branches Tags
vvzvlad:main-6sep
vvzvlad:XGBRegressor-v2
vvzvlad:XGBRegressor-v1
vvzvlad:lasso-1
vvzvlad:main
..
compare: vvzvlad:main-6sep
Branches Tags
vvzvlad:main-6sep
vvzvlad:XGBRegressor-v2
vvzvlad:XGBRegressor-v1
vvzvlad:lasso-1
vvzvlad:main

No commits in common. "XGBRegressor-v1" and "main-6sep" have entirely different histories.
XGBRegress ... main-6sep

17 changed files with 1193 additions and 243 deletions
Show Stats Expand all files Collapse all files

7
.env Normal file
View File

@ -0,0 +1,7 @@
TOKEN=###TOKEN###
TRAINING_DAYS=###TRAINING_DAYS###
TIMEFRAME=###TIMEFRAME###
MODEL=###MODEL###
REGION=EU
DATA_PROVIDER=###DATA_PROVIDER###
CG_API_KEY=###CG_API_KEY###

19
.gitignore vendored Normal file
View File

@ -0,0 +1,19 @@
.DS_Store
__pycache__
*.pyc
logs/*
.allorad
.cache
inference-data
worker-data
/data
**/*.venv*
**/.cache
**/env_file
**/.gitkeep*
**/*.csv
**/*.pkl
**/*.zip

18
CONTRIBUTING.md Normal file
View File

@ -0,0 +1,18 @@
Any contribution that you make to this repository will
be under the Apache 2 License, as dictated by that
[license](http://www.apache.org/licenses/LICENSE-2.0.html):
~~~
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
~~~
Contributors must sign-off each commit by adding a `Signed-off-by: ...`
line to commit messages to certify that they have the right to submit
the code they are contributing to the project according to the
[Developer Certificate of Origin (DCO)](https://developercertificate.org/).

6
Dockerfile
View File

@ -1,5 +1,7 @@
# Use an official Python runtime as the base image
FROM amd64/python:3.9-buster as project_env
FROM python:3.11-slim AS project_env
# Install curl
RUN apt-get update && apt-get install -y curl
# Set the working directory in the container
WORKDIR /app

201
LICENSE Normal file
View File

@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

112
README.md Normal file
View File

@ -0,0 +1,112 @@
# Basic Price Prediction Node
This repository provides an example [Allora network](https://docs.allora.network/) worker node, designed to offer price predictions. The primary objective is to demonstrate the use of a basic inference model running within a dedicated container, showcasing its integration with the Allora network infrastructure to contribute valuable inferences.
## Components
- **Worker**: The node that publishes inferences to the Allora chain.
- **Inference**: A container that conducts inferences, maintains the model state, and responds to internal inference requests via a Flask application. This node operates with a basic linear regression model for price predictions.
- **Updater**: A cron-like container designed to update the inference node's data by daily fetching the latest market information from the data provider, ensuring the model stays current with new market trends.
Check the `docker-compose.yml` file for the detailed setup of each component.
## Docker-Compose Setup
A complete working example is provided in the `docker-compose.yml` file.
### Steps to Setup
1. **Clone the Repository**
2. **Copy and Populate Model Configuration environment file**
Copy the example .env.example file and populate it with your variables:
```sh
cp .env.example .env
```
Here are the currently accepted configurations:
- TOKEN
Must be one in ('ETH','SOL','BTC','BNB','ARB').
Note: if you are using `Binance` as the data provider, any token could be used.
If you are using Coingecko, you should add its `coin_id` in the [token_map here](https://github.com/allora-network/basic-coin-prediction-node/blob/main/updater.py#L107). Find [more info here](https://docs.coingecko.com/reference/simple-price) and the [list here](https://docs.google.com/spreadsheets/d/1wTTuxXt8n9q7C4NDXqQpI3wpKu1_5bGVmP9Xz0XGSyU/edit?usp=sharing).
- TRAINING_DAYS
Must be an `int` >= 1.
Represents how many days of historical data to use.
- TIMEFRAME
This should be in this form: `10min`, `1h`, `1d`, `1m`, etc.
Note: For Coingecko, Data granularity (candle's body) is automatic - [see here](https://docs.coingecko.com/reference/coins-id-ohlc). To avoid downsampling, it is recommanded to use with Coingecko:
- TIMEFRAME >= 30m if TRAINING_DAYS <= 2
- TIMEFRAME >= 4h if TRAINING_DAYS <= 30
- TIMEFRAME >= 4d if TRAINING_DAYS >= 31
- MODEL
Must be one in ('LinearRegression','SVR','KernelRidge','BayesianRidge').
You can easily add support for any other models by [adding it here](https://github.com/allora-network/basic-coin-prediction-node/blob/main/model.py#L133).
- REGION
Used for the Binance API. This should be in this form: `US`, `EU`, etc.
- DATA_PROVIDER
Must be `binance` or `coingecko`. Feel free to add support for other data providers to personalize your model!
- CG_API_KEY
This is your `Coingecko` API key, if you've set `DATA_PROVIDER=coingecko`.
3. **Copy and Populate Worker Configuration**
Copy the example configuration file and populate it with your variables:
```sh
cp config.example.json config.json
```
4. **Initialize Worker**
Run the following commands from the project's root directory to initialize the worker:
```sh
chmod +x init.config
./init.config
```
These commands will:
- Automatically create Allora keys for your worker.
- Export the needed variables from the created account to be used by the worker node, bundle them with your provided `config.json`, and pass them to the node as environment variables.
5. **Faucet Your Worker Node**
You can find the offchain worker node's address in `./worker-data/env_file` under `ALLORA_OFFCHAIN_ACCOUNT_ADDRESS`. [Add faucet funds](https://docs.allora.network/devs/get-started/setup-wallet#add-faucet-funds) to your worker's wallet before starting it.
6. **Start the Services**
Run the following command to start the worker node, inference, and updater nodes:
```sh
docker compose up --build
```
To confirm that the worker successfully sends the inferences to the chain, look for the following log:
```
{"level":"debug","msg":"Send Worker Data to chain","txHash":<tx-hash>,"time":<timestamp>,"message":"Success"}
```
## Testing Inference Only
This setup allows you to develop your model without the need to bring up the offchain worker or the updater. To test the inference model only:
1. Run the following command to start the inference node:
```sh
docker compose up --build inference
```
Wait for the initial data load.
2. Send requests to the inference model. For example, request ETH price inferences:
```sh
curl http://127.0.0.1:8000/inference/ETH
```
Expected response:
```json
{"value":"2564.021586281073"}
```
3. Update the node's internal state (download pricing data, train, and update the model):
```sh
curl http://127.0.0.1:8000/update
```
Expected response:
```sh
0
```

65
app.py
View File

@ -1,72 +1,31 @@
import json
import pickle
import pandas as pd
import numpy as np
from datetime import datetime
from flask import Flask, jsonify, Response
from model import download_data, format_data, train_model, training_price_data_path
from config import model_file_path
from flask import Flask, Response
from model import download_data, format_data, train_model, get_inference
from config import model_file_path, TOKEN, TIMEFRAME, TRAINING_DAYS, REGION, DATA_PROVIDER
app = Flask(__name__)
def update_data():
"""Download price data, format data and train model."""
download_data()
format_data()
train_model()
def get_eth_inference():
"""Load model and predict current price."""
try:
with open(model_file_path, "rb") as f:
loaded_model = pickle.load(f)
# Загружаем последние данные из файла
price_data = pd.read_csv(training_price_data_path)
# Используем последние значения признаков для предсказания
X_new = (
price_data[
[
"timestamp",
"price_diff",
"volatility",
"volume",
"moving_avg_7",
"moving_avg_30",
]
]
.iloc[-1]
.values.reshape(1, -1)
)
# Делаем предсказание
current_price_pred = loaded_model.predict(X_new)
return current_price_pred[0]
except Exception as e:
print(f"Error during inference: {str(e)}")
raise
files = download_data(TOKEN, TRAINING_DAYS, REGION, DATA_PROVIDER)
format_data(files, DATA_PROVIDER)
train_model(TIMEFRAME)
@app.route("/inference/<string:token>")
def generate_inference(token):
"""Generate inference for given token."""
if not token or token != "ETH":
if not token or token.upper() != TOKEN:
error_msg = "Token is required" if not token else "Token not supported"
return Response(
json.dumps({"error": error_msg}), status=400, mimetype="application/json"
)
return Response(json.dumps({"error": error_msg}), status=400, mimetype='application/json')
try:
inference = get_eth_inference()
inference = get_inference(token.upper(), TIMEFRAME, REGION, DATA_PROVIDER)
return Response(str(inference), status=200)
except Exception as e:
return Response(
json.dumps({"error": str(e)}), status=500, mimetype="application/json"
)
return Response(json.dumps({"error": str(e)}), status=500, mimetype='application/json')
@app.route("/update")
@ -81,4 +40,4 @@ def update():
if __name__ == "__main__":
update_data()
app.run(host="0.0.0.0", port=8000)
app.run(host="0.0.0.0", port=8000)

30
config.json
View File

@ -3,39 +3,21 @@
"addressKeyName": "###WALLET###",
"addressRestoreMnemonic": "###MNEMONIC###",
"alloraHomeDir": "",
"gas": "1000000",
"gasAdjustment": 1.0,
"gas": "auto",
"gasAdjustment": 1.5,
"nodeRpc": "###RPC_URL###",
"maxRetries": 10,
"delay": 30,
"submitTx": false
"delay": 20,
"submitTx": true
},
"worker": [
{
"topicId": 1,
"topicId": ###TOPIC###,
"inferenceEntrypointName": "api-worker-reputer",
"loopSeconds": 5,
"parameters": {
"InferenceEndpoint": "http://inference:8000/inference/{Token}",
"Token": "ETH"
}
},
{
"topicId": 2,
"inferenceEntrypointName": "api-worker-reputer",
"loopSeconds": 5,
"parameters": {
"InferenceEndpoint": "http://inference:8000/inference/{Token}",
"Token": "ETH"
}
},
{
"topicId": 7,
"inferenceEntrypointName": "api-worker-reputer",
"loopSeconds": 5,
"parameters": {
"InferenceEndpoint": "http://inference:8000/inference/{Token}",
"Token": "ETH"
"Token": "###TOKEN###"
}
}
]

16
config.py
View File

@ -1,5 +1,21 @@
import os
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
app_base_path = os.getenv("APP_BASE_PATH", default=os.getcwd())
data_base_path = os.path.join(app_base_path, "data")
model_file_path = os.path.join(data_base_path, "model.pkl")
TOKEN = os.getenv("TOKEN").upper()
TRAINING_DAYS = os.getenv("TRAINING_DAYS")
TIMEFRAME = os.getenv("TIMEFRAME")
MODEL = os.getenv("MODEL")
REGION = os.getenv("REGION").lower()
if REGION in ["us", "com", "usa"]:
REGION = "us"
else:
REGION = "com"
DATA_PROVIDER = os.getenv("DATA_PROVIDER").lower()
CG_API_KEY = os.getenv("CG_API_KEY", default=None)

15
docker-compose.yml
View File

@ -1,21 +1,22 @@
services:
inference:
container_name: inference-basic-eth-pred
container_name: inference
env_file:
- .env
build: .
command: python -u /app/app.py
ports:
- "8000:8000"
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8000/inference/ETH"]
test: ["CMD", "curl", "-f", "http://inference:8000/inference/${TOKEN}"]
interval: 10s
timeout: 5s
retries: 12
volumes:
- ./inference-data:/app/data
restart: always
updater:
container_name: updater-basic-eth-pred
container_name: updater
build: .
environment:
- INFERENCE_API_ADDRESS=http://inference:8000
@ -29,11 +30,10 @@ services:
depends_on:
inference:
condition: service_healthy
restart: always
worker:
container_name: worker
image: alloranetwork/allora-offchain-node:latest
image: alloranetwork/allora-offchain-node:v0.3.0
volumes:
- ./worker-data:/data
depends_on:
@ -41,7 +41,6 @@ services:
condition: service_healthy
env_file:
- ./worker-data/env_file
restart: always
volumes:
inference-data:

6
init.config
View File

@ -1,4 +1,4 @@
#!/usr/bin/env bash
#!/bin/bash
set -e
@ -25,7 +25,7 @@ if [ -n "$mnemonic" ]; then
echo "NAME=$nodeName" >> ./worker-data/env_file
echo "ENV_LOADED=true" >> ./worker-data/env_file
echo "wallet mnemonic already provided by you, loading config.json . Please proceed to run docker compose"
exit 0
exit 1
fi
if [ ! -f ./worker-data/env_file ]; then
@ -36,7 +36,7 @@ ENV_LOADED=$(grep '^ENV_LOADED=' ./worker-data/env_file | cut -d '=' -f 2)
if [ "$ENV_LOADED" = "false" ]; then
json_content=$(cat ./config.json)
stringified_json=$(echo "$json_content" | jq -c .)
docker run -it --entrypoint=bash -v $(pwd)/worker-data:/data -v $(pwd)/scripts:/scripts -e NAME="${nodeName}" -e ALLORA_OFFCHAIN_NODE_CONFIG_JSON="${stringified_json}" alloranetwork/allora-chain:latest -c "bash /scripts/init.sh"
docker run -it --entrypoint=bash -v $(pwd)/worker-data:/data -v $(pwd)/scripts:/scripts -e NAME="${nodeName}" -e ALLORA_OFFCHAIN_NODE_CONFIG_JSON="${stringified_json}" alloranetwork/allora-chain:v0.4.0 -c "bash /scripts/init.sh"
echo "config.json saved to ./worker-data/env_file"
else
echo "config.json is already loaded, skipping the operation. You can set ENV_LOADED variable to false in ./worker-data/env_file to reload the config.json"

3
logs_parser.py
View File

@ -47,6 +47,9 @@ def parse_logs(timeout):
if current_retry == max_retry:
print(f"Max Retry Reached: {data}", flush=True)
return False, "Max Retry Reached"
elif data.get("message") == "Error getting latest open worker nonce on topic":
print(f"Error: {data}", flush=True)
return False, "Error getting latest open worker nonce on topic"
except Exception as e:
print(f"Exception occurred: {e}", flush=True)

225
model.py
View File

@ -1,108 +1,148 @@
import json
import os
import pickle
import numpy as np
from xgboost import XGBRegressor
from zipfile import ZipFile
from datetime import datetime
import pandas as pd
from sklearn.model_selection import train_test_split
from updater import download_binance_monthly_data, download_binance_daily_data
from config import data_base_path, model_file_path
binance_data_path = os.path.join(data_base_path, "binance/futures-klines")
training_price_data_path = os.path.join(data_base_path, "eth_price_data.csv")
from sklearn.kernel_ridge import KernelRidge
from sklearn.linear_model import BayesianRidge, LinearRegression
from sklearn.svm import SVR
from updater import download_binance_daily_data, download_binance_current_day_data, download_coingecko_data, download_coingecko_current_day_data
from config import data_base_path, model_file_path, TOKEN, MODEL, CG_API_KEY
def download_data():
cm_or_um = "um"
symbols = ["ETHUSDT"]
intervals = ["1d"]
years = ["2020", "2021", "2022", "2023", "2024"]
months = ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12"]
download_path = binance_data_path
download_binance_monthly_data(
cm_or_um, symbols, intervals, years, months, download_path
)
print(f"Downloaded monthly data to {download_path}.")
current_datetime = datetime.now()
current_year = current_datetime.year
current_month = current_datetime.month
download_binance_daily_data(
cm_or_um, symbols, intervals, current_year, current_month, download_path
)
print(f"Downloaded daily data to {download_path}.")
binance_data_path = os.path.join(data_base_path, "binance")
coingecko_data_path = os.path.join(data_base_path, "coingecko")
training_price_data_path = os.path.join(data_base_path, "price_data.csv")
def format_data():
files = sorted([x for x in os.listdir(binance_data_path) if x.endswith(".zip")])
def download_data_binance(token, training_days, region):
files = download_binance_daily_data(f"{token}USDT", training_days, region, binance_data_path)
print(f"Downloaded {len(files)} new files")
return files
def download_data_coingecko(token, training_days):
files = download_coingecko_data(token, training_days, coingecko_data_path, CG_API_KEY)
print(f"Downloaded {len(files)} new files")
return files
def download_data(token, training_days, region, data_provider):
if data_provider == "coingecko":
return download_data_coingecko(token, int(training_days))
elif data_provider == "binance":
return download_data_binance(token, training_days, region)
else:
raise ValueError("Unsupported data provider")
def format_data(files, data_provider):
if not files:
print("Already up to date")
return
if data_provider == "binance":
files = sorted([x for x in os.listdir(binance_data_path) if x.startswith(f"{TOKEN}USDT")])
elif data_provider == "coingecko":
files = sorted([x for x in os.listdir(coingecko_data_path) if x.endswith(".json")])
# No files to process
if len(files) == 0:
return
price_df = pd.DataFrame()
for file in files:
zip_file_path = os.path.join(binance_data_path, file)
myzip = ZipFile(zip_file_path)
with myzip.open(myzip.filelist[0]) as f:
line = f.readline()
header = 0 if line.decode("utf-8").startswith("open_time") else None
df = pd.read_csv(myzip.open(myzip.filelist[0]), header=header).iloc[:, :11]
df.columns = [
"start_time",
"open",
"high",
"low",
"close",
"volume",
"end_time",
"volume_usd",
"n_trades",
"taker_volume",
"taker_volume_usd",
]
df.index = [pd.Timestamp(x + 1, unit="ms") for x in df["end_time"]]
df.index.name = "date"
price_df = pd.concat([price_df, df])
if data_provider == "binance":
for file in files:
zip_file_path = os.path.join(binance_data_path, file)
price_df["timestamp"] = price_df.index.map(pd.Timestamp.timestamp)
price_df["price_diff"] = price_df["close"].diff()
price_df["volatility"] = (price_df["high"] - price_df["low"]) / price_df["open"]
price_df["volume"] = price_df["volume"]
price_df["moving_avg_7"] = price_df["close"].rolling(window=7).mean()
price_df["moving_avg_30"] = price_df["close"].rolling(window=30).mean()
if not zip_file_path.endswith(".zip"):
continue
# Удаляем строки с NaN значениями
price_df.dropna(inplace=True)
myzip = ZipFile(zip_file_path)
with myzip.open(myzip.filelist[0]) as f:
line = f.readline()
header = 0 if line.decode("utf-8").startswith("open_time") else None
df = pd.read_csv(myzip.open(myzip.filelist[0]), header=header).iloc[:, :11]
df.columns = [
"start_time",
"open",
"high",
"low",
"close",
"volume",
"end_time",
"volume_usd",
"n_trades",
"taker_volume",
"taker_volume_usd",
]
df.index = [pd.Timestamp(x + 1, unit="ms").to_datetime64() for x in df["end_time"]]
df.index.name = "date"
price_df = pd.concat([price_df, df])
# Сохраняем данные
price_df.sort_index().to_csv(training_price_data_path)
price_df.sort_index().to_csv(training_price_data_path)
elif data_provider == "coingecko":
for file in files:
with open(os.path.join(coingecko_data_path, file), "r") as f:
data = json.load(f)
df = pd.DataFrame(data)
df.columns = [
"timestamp",
"open",
"high",
"low",
"close"
]
df["date"] = pd.to_datetime(df["timestamp"], unit="ms")
df.drop(columns=["timestamp"], inplace=True)
df.set_index("date", inplace=True)
price_df = pd.concat([price_df, df])
price_df.sort_index().to_csv(training_price_data_path)
def train_model():
def load_frame(frame, timeframe):
print(f"Loading data...")
df = frame.loc[:,['open','high','low','close']].dropna()
df[['open','high','low','close']] = df[['open','high','low','close']].apply(pd.to_numeric)
df['date'] = frame['date'].apply(pd.to_datetime)
df.set_index('date', inplace=True)
df.sort_index(inplace=True)
return df.resample(f'{timeframe}', label='right', closed='right', origin='end').mean()
def train_model(timeframe):
# Load the price data
price_data = pd.read_csv(training_price_data_path)
df = load_frame(price_data, timeframe)
# Используем дополнительные признаки
x = price_data[
[
"timestamp",
"price_diff",
"volatility",
"volume",
"moving_avg_7",
"moving_avg_30",
]
]
y = price_data["close"]
x_train, x_test, y_train, y_test = train_test_split(
x, y, test_size=0.2, random_state=0
)
if df.empty:
raise ValueError("No data available after loading and formatting. Check the data source or timeframe.")
print(df.tail())
y_train = df['close'].shift(-1).dropna().values
X_train = df[:-1]
if X_train.empty or len(y_train) == 0:
raise ValueError("Training data is empty. Ensure there is enough data for training.")
print(f"Training data shape: {X_train.shape}, {y_train.shape}")
# Define the model
if MODEL == "LinearRegression":
model = LinearRegression()
elif MODEL == "SVR":
model = SVR()
elif MODEL == "KernelRidge":
model = KernelRidge()
elif MODEL == "BayesianRidge":
model = BayesianRidge()
# Add more models here
else:
raise ValueError("Unsupported model")
# Train the model
print("Training model...")
model = XGBRegressor()
model.fit(x_train, y_train)
print("Model trained.")
model.fit(X_train, y_train)
# create the model's parent directory if it doesn't exist
os.makedirs(os.path.dirname(model_file_path), exist_ok=True)
@ -113,6 +153,21 @@ def train_model():
print(f"Trained model saved to {model_file_path}")
# Optional: Оценка модели
y_pred = model.predict(x_test)
print(f"Mean Absolute Error: {np.mean(np.abs(y_test - y_pred))}")
def get_inference(token, timeframe, region, data_provider):
"""Load model and predict current price."""
with open(model_file_path, "rb") as f:
loaded_model = pickle.load(f)
# Get current price
if data_provider == "coingecko":
X_new = load_frame(download_coingecko_current_day_data(token, CG_API_KEY), timeframe)
else:
X_new = load_frame(download_binance_current_day_data(f"{TOKEN}USDT", region), timeframe)
print(X_new.tail())
print(X_new.shape)
current_price_pred = loaded_model.predict(X_new)
return current_price_pred[0]

470
playbook.yml Normal file
View File

@ -0,0 +1,470 @@
- name: Allora deployment playbook
hosts: all
become: true
vars:
ansible_python_interpreter: /usr/bin/python3.11
ipfs_url: https://bafybeigpiwl3o73zvvl6dxdqu7zqcub5mhg65jiky2xqb4rdhfmikswzqm.ipfs.w3s.link/manifest.json
tasks:
- name: Append command to .bash_history
ansible.builtin.blockinfile:
path: "~/.bash_history"
create: true
block: |
#1724983098
cd basic-coin-prediction-node/ ; docker compose logs -f
#1724983099
docker logs worker -f
cd basic-coin-prediction-node/ ; docker compose up
marker: ""
mode: '0644'
- name: Set locale to C.UTF-8
ansible.builtin.command:
cmd: localectl set-locale LANG=C.UTF-8
changed_when: false
- name: Create APT configuration file to assume yes
ansible.builtin.copy:
dest: /etc/apt/apt.conf.d/90forceyes
content: |
APT::Get::Assume-Yes "true";
mode: '0644'
- name: Update /etc/bash.bashrc
ansible.builtin.blockinfile:
path: /etc/bash.bashrc
block: |
export HISTTIMEFORMAT='%F, %T '
export HISTSIZE=10000
export HISTFILESIZE=10000
shopt -s histappend
export PROMPT_COMMAND='history -a'
export HISTCONTROL=ignoredups
export LANG=C.UTF-8
export LC_ALL=C.UTF-8
alias ls='ls --color=auto'
shopt -s cmdhist
- name: Ensure ~/.inputrc exists
ansible.builtin.file:
path: /root/.inputrc
state: touch
mode: '0644'
- name: Update ~/.inputrc
ansible.builtin.blockinfile:
path: ~/.inputrc
block: |
"\e[A": history-search-backward
"\e[B": history-search-forward
- name: Ensure ~/.nanorc exists
ansible.builtin.file:
path: /root/.nanorc
state: touch
mode: '0644'
- name: Update ~/.nanorc
ansible.builtin.blockinfile:
path: ~/.nanorc
block: |
set nohelp
set tabsize 4
set tabstospaces
set autoindent
set positionlog
set backup
set backupdir /tmp/
set locking
include /usr/share/nano/*.nanorc
- name: Set hostname
ansible.builtin.shell: |
hostnamectl set-hostname {{ serverid }}
echo "127.0.1.1 {{ serverid }}" >> /etc/hosts
changed_when: false
- name: Update apt cache
ansible.builtin.apt:
update_cache: true
register: apt_update_result
retries: 5
delay: 50
until: apt_update_result is succeeded
- name: Upgrade packages
ansible.builtin.apt:
upgrade: dist
force_apt_get: true
autoremove: true
register: apt_upgrade_result
retries: 5
delay: 50
until: apt_upgrade_result is succeeded
# - name: Install packages
# ansible.builtin.apt:
# name:
# - ca-certificates
# - zlib1g-dev
# - libncurses5-dev
# - libgdbm-dev
# - libnss3-dev
# - curl
# - jq
# - git
# - zip
# - wget
# - make
# - python3
# - python3-pip
# - iftop
# state: present
# update_cache: true
# async: "{{ 60 * 20 }}"
# poll: 30
# - name: Check no-proxy ipfs access
# ansible.builtin.shell: |
# curl -s -w "%{http_code}" -o response.json {{ ipfs_url }}
# register: noproxy_check
# changed_when: false
# failed_when: noproxy_check.stdout != "200"
#
# - name: Check proxy ipfs access
# ansible.builtin.shell: |
# curl -s -w "%{http_code}" -o response.json -x {{ proxy }} {{ ipfs_url }}
# register: proxy_check
# changed_when: false
# failed_when: proxy_check.stdout != "200"
# - name: Install Docker
# ansible.builtin.shell: curl -fsSL https://get.docker.com | bash
# changed_when: false
# async: "{{ 60 * 5 }}"
# poll: 30
# - name: Update Docker daemon journald logging
# ansible.builtin.copy:
# dest: /etc/docker/daemon.json
# content: |
# {
# "log-driver": "journald"
# }
# mode: '0644'
#
# - name: Restart Docker
# ansible.builtin.service:
# name: docker
# state: restarted
#
# - name: Update journald log SystemMaxUse=2G configuration
# ansible.builtin.lineinfile:
# path: /etc/systemd/journald.conf
# line: 'SystemMaxUse=2G'
# insertafter: EOF
# create: true
# mode: '0644'
#
# - name: Restart journald
# ansible.builtin.service:
# name: systemd-journald
# state: restarted
- name: Docker login
ansible.builtin.shell: docker login -u "{{ docker_username }}" -p "{{ docker_password }}"
register: docker_login_result
changed_when: false
failed_when: "'Login Succeeded' not in docker_login_result.stdout"
- name: Clone repository
ansible.builtin.git:
repo: https://gitea.vvzvlad.xyz/vvzvlad/allora
dest: "{{ ansible_env.HOME }}/basic-coin-prediction-node"
version: "{{ git_version }}"
force: true
async: "{{ 60 * 15 }}"
poll: 30
- name: Update environment variables
ansible.builtin.shell: |
./update.sh WALLET "{{ wallet }}"
./update.sh MNEMONIC "{{ mnemonic }}"
./update.sh RPC_URL "{{ rpc_url }}"
./update.sh TOKEN "{{ token }}"
./update.sh TOPIC "{{ topic }}"
./update.sh TRAINING_DAYS "{{ training_days }}"
./update.sh TIMEFRAME "{{ timeframe }}"
./update.sh MODEL "{{ model }}"
./update.sh DATA_PROVIDER "{{ data_provider }}"
./update.sh CG_API_KEY "{{ cg_api_key }}"
args:
chdir: "{{ ansible_env.HOME }}/basic-coin-prediction-node"
changed_when: false
- name: Init config
ansible.builtin.shell: ./init.config ; true
args:
chdir: "{{ ansible_env.HOME }}/basic-coin-prediction-node"
changed_when: false
- name: Build docker compose
ansible.builtin.command: docker compose build -q
args:
chdir: "{{ ansible_env.HOME }}/basic-coin-prediction-node"
environment:
COMPOSE_INTERACTIVE_NO_CLI: 'true'
changed_when: false
async: "{{ 60 * 45 }}"
poll: "{{ 60 * 5 }}"
# - name: Docker pre-up
# ansible.builtin.command: docker compose up -d
# args:
# chdir: "{{ ansible_env.HOME }}/basic-coin-prediction-node"
# environment:
# COMPOSE_INTERACTIVE_NO_CLI: 'true'
# changed_when: false
# async: "{{ 60 * 80 }}"
# poll: "{{ 60 * 5 }}"
# - name: Check Docker container status
# ansible.builtin.shell: >
# if [ $(docker ps -q | wc -l) -eq $(docker ps -a -q | wc -l) ]; then
# echo "all_running";
# else
# echo "not_all_running";
# fi
# register: container_status
# retries: 10
# delay: 30
# until: container_status.stdout.find("all_running") != -1
#
# - name: Docker stop (pre-up)
# ansible.builtin.command: docker compose stop
# args:
# chdir: "{{ ansible_env.HOME }}/basic-coin-prediction-node"
# environment:
# COMPOSE_INTERACTIVE_NO_CLI: 'true'
# changed_when: false
#
# - name: Check external IP before
# ansible.builtin.command: curl https://ifconfig.me
# register: ip_before
# changed_when: false
#
# - name: Validate IP address
# ansible.builtin.assert:
# that:
# - ip_before.stdout | ansible.utils.ipaddr
# fail_msg: "The returned value is not a valid IP address."
# success_msg: "The returned value is a valid IP address."
# - name: Download tun2socks
# ansible.builtin.get_url:
# url: https://github.com/xjasonlyu/tun2socks/releases/download/v2.5.2/tun2socks-linux-amd64.zip
# dest: /tmp/tun2socks-linux-amd64.zip
# mode: '0644'
# async: "{{ 60 * 5 }}"
# poll: 30
#
# - name: Unzip tun2socks
# ansible.builtin.unarchive:
# src: /tmp/tun2socks-linux-amd64.zip
# dest: /usr/local/sbin/
# remote_src: true
# mode: '0755'
#
# - name: Create proxy file
# ansible.builtin.copy:
# content: "{{ proxy }}"
# dest: /root/proxy
# mode: '0644'
#
# - name: Create tun2socks systemd service
# ansible.builtin.copy:
# dest: /etc/systemd/system/tun2socks.service
# content: |
# [Unit]
# Description=Tun2Socks gateway
# After=network.target
# Wants=network.target
#
# [Service]
# User=root
# Type=simple
# RemainAfterExit=true
# ExecStartPre=/bin/sh -c 'ip route add $(cat /root/proxy | grep -oP "(?<=@)[0-9.]+(?=:)" )/32 via $(ip route | grep -oP "(?<=default via )[0-9.]+")'
# ExecStart=/bin/sh -c '/usr/local/sbin/tun2socks-linux-amd64 --device tun0 --proxy $(cat /root/proxy)'
# ExecStopPost=/bin/sh -c 'ip route del $(cat /root/proxy | grep -oP "(?<=@)[0-9.]+(?=:)" )/32 via $(ip route | grep -oP "(?<=default via )[0-9.]+")'
# Restart=always
#
# [Install]
# WantedBy=multi-user.target
# mode: '0644'
#
# - name: Create network configuration for tun0
# ansible.builtin.copy:
# dest: /etc/systemd/network/10-proxy.network
# content: |
# [Match]
# Name=tun0
#
# [Network]
# Address=10.20.30.1/24
#
# [Route]
# Gateway=0.0.0.0
# mode: '0644'
#
# - name: Enable and start tun2socks service
# ansible.builtin.systemd:
# name: tun2socks
# enabled: true
# state: started
#
# - name: Reload network configuration
# ansible.builtin.command: networkctl reload
# changed_when: false
#
# - name: Restart tun2socks service
# ansible.builtin.systemd:
# name: tun2socks
# state: restarted
- name: Check RPC availability
ansible.builtin.uri:
url: "{{ rpc_url }}/health?"
method: GET
return_content: true
timeout: 30
register: rpc_url_response
retries: 3
delay: 120
failed_when:
- rpc_url_response.status != 200
- rpc_url_response.json is not none and rpc_url_response.json is not defined
- name: Check Binance URL availability
ansible.builtin.uri:
url: "https://api.binance.com/api/v3/klines?symbol=BTCUSDT&interval=1M&limit=1"
method: GET
return_content: true
register: binance_url_response
retries: 3
delay: 60
failed_when:
- binance_url_response.status != 200
- binance_url_response.json is not none and binance_url_response.json is not defined
# - name: Get balance for the wallet
# retries: 3
# delay: 30
# ansible.builtin.shell: |
# response=$(curl --silent --location --request GET "https://allora-api.testnet.allora.network/cosmos/bank/v1beta1/balances/{{ wallet }}") && \
# echo "$response" && \
# uallo_balance=$(echo "$response" | jq -r '.balances[] | select(.denom == "uallo") | .amount // 0') && \
# echo "uallo_balance: $uallo_balance" && \
# if [ "$uallo_balance" -gt 100000 ]; then
# echo "Balance {{ wallet }} > 100000"
# else
# echo "Balance {{ wallet }} < 100000"
# exit 1
# fi
# register: wallet_balance_check
# failed_when: wallet_balance_check.rc != 0
# - name: Check external IP after
# ansible.builtin.command: curl https://ifconfig.me
# register: ip_after
# changed_when: false
#
# - name: Validate IP address
# ansible.builtin.assert:
# that:
# - ip_after.stdout | ansible.utils.ipaddr
# fail_msg: "The returned value is not a valid IP address."
# success_msg: "The returned value is a valid IP address."
#
# - name: Show IPs
# ansible.builtin.debug:
# msg: "External IP before: {{ ip_before.stdout }}, External IP after: {{ ip_after.stdout }}"
#
# - name: Compare external IPs
# ansible.builtin.fail:
# msg: "External IP before and after should not be the same"
# when: ip_before.stdout == ip_after.stdout
- name: Docker up
ansible.builtin.command: docker compose up -d
args:
chdir: "{{ ansible_env.HOME }}/basic-coin-prediction-node"
environment:
COMPOSE_INTERACTIVE_NO_CLI: 'true'
changed_when: false
async: "{{ 60 * 80 }}"
poll: "{{ 60 * 5 }}"
- name: Check Docker containers status
ansible.builtin.shell: >
if [ $(docker ps -q | wc -l) -eq $(docker ps -a -q | wc -l) ]; then
echo "all_running";
else
echo "not_all_running";
fi
register: container_status
retries: 10
delay: 30
until: container_status.stdout.find("all_running") != -1
- name: Check "not have enough balance"
ansible.builtin.command: docker logs {{ item }} 2>&1
register: docker_logs_check
changed_when: false
failed_when: '"not have enough balance" in docker_logs_check.stdout'
with_items:
- worker
- worker-1
- worker-2
- name: Check updater endpoint
ansible.builtin.shell: |
response=$(curl --silent --location --request GET http://localhost:8000/update) && \
if [ "$response" != "0" ]; then
echo "Updater endpoint check failed: $response != 0"
exit 1
fi
register: updater_shell_response
retries: 2
delay: 60
until: updater_shell_response.rc == 0
changed_when: false
- name: Check inference endpoint
ansible.builtin.shell: |
response=$(curl --silent --location --request GET http://localhost:8000/inference/{{ token }}) && \
status=$(curl -o /dev/null -s -w "%{http_code}\\n" http://localhost:8000/inference/{{ token }}) && \
if [ "$status" -ne 200 ] || ! echo "$response" | grep -qE '^[0-9]+(\.[0-9]+)?$'; then
echo "Inference endpoint check failed: status $status, response $response"
exit 1
fi
register: inference_shell_response
retries: 2
delay: 60
failed_when: inference_shell_response.rc != 0
changed_when: false
# - name: Wait success send
# ansible.builtin.shell: |
# python3 logs_parser.py 80
# args:
# chdir: "{{ ansible_env.HOME }}/basic-coin-prediction-node"
# register: docker_logs_check
# changed_when: false
# failed_when: docker_logs_check.rc != 0
- name: Remove docker login credentials
ansible.builtin.file:
path: /root/.docker/config.json
state: absent

21
requirements.txt
View File

@ -1,16 +1,9 @@
flask[async]
gunicorn[gthread]
numpy==1.26.2
pandas==2.1.3
Requests==2.32.0
scikit_learn==1.3.2
werkzeug>=3.0.3 # not directly required, pinned by Snyk to avoid a vulnerability
itsdangerous
Jinja2
MarkupSafe
python-dateutil
pytz
scipy
six
scikit-learn
xgboost
numpy
pandas
Requests
aiohttp
multiprocess
scikit_learn
python-dotenv

18
update.sh
View File

@ -1,22 +1,20 @@
#!/usr/bin/env bash
if [ "$#" -ne 3 ]; then
echo "Usage: $0 <mnemonic> <wallet> <rpc_url>"
if [ "$#" -ne 2 ]; then
echo "Usage: $0 <PARAMETER> <NEW_VALUE>"
exit 1
fi
MNEMONIC=$1
WALLET=$2
RPC_URL=$3
PARAMETER=$1
NEW_VALUE=$2
# List of files
# Список файлов
FILES=(
"./config.json"
".env"
)
for FILE in "${FILES[@]}"; do
EXPANDED_FILE=$(eval echo "$FILE")
sed -i "s|###MNEMONIC###|$MNEMONIC|g" "$EXPANDED_FILE"
sed -i "s|###WALLET###|$WALLET|g" "$EXPANDED_FILE"
sed -i "s|###RPC_URL###|$RPC_URL|g" "$EXPANDED_FILE"
done
sed -i "s|###$PARAMETER###|$NEW_VALUE|g" "$EXPANDED_FILE"
done

204
updater.py
View File

@ -1,59 +1,175 @@
import os
from datetime import date, timedelta
import pathlib
import time
import requests
from requests.adapters import HTTPAdapter
from urllib3.util import Retry
from concurrent.futures import ThreadPoolExecutor
import pandas as pd
import json
# Define the retry strategy
retry_strategy = Retry(
total=4, # Maximum number of retries
backoff_factor=2, # Exponential backoff factor (e.g., 2 means 1, 2, 4, 8 seconds, ...)
status_forcelist=[429, 500, 502, 503, 504], # HTTP status codes to retry on
)
# Create an HTTP adapter with the retry strategy and mount it to session
adapter = HTTPAdapter(max_retries=retry_strategy)
# Create a new session object
session = requests.Session()
session.mount('http://', adapter)
session.mount('https://', adapter)
files = []
# Function to download the URL, called asynchronously by several child processes
def download_url(url, download_path):
target_file_path = os.path.join(download_path, os.path.basename(url))
if os.path.exists(target_file_path):
# print(f"File already exists: {url}")
return
def download_url(url, download_path, name=None):
try:
global files
if name:
file_name = os.path.join(download_path, name)
else:
file_name = os.path.join(download_path, os.path.basename(url))
dir_path = os.path.dirname(file_name)
pathlib.Path(dir_path).mkdir(parents=True, exist_ok=True)
if os.path.isfile(file_name):
# print(f"{file_name} already exists")
return
# Make a request using the session object
response = session.get(url)
if response.status_code == 404:
print(f"File does not exist: {url}")
elif response.status_code == 200:
with open(file_name, 'wb') as f:
f.write(response.content)
# print(f"Downloaded: {url} to {file_name}")
files.append(file_name)
return
else:
print(f"Failed to download {url}")
return
except Exception as e:
print(str(e))
# Function to generate a range of dates
def daterange(start_date, end_date):
for n in range(int((end_date - start_date).days)):
yield start_date + timedelta(n)
# Function to download daily data from Binance
def download_binance_daily_data(pair, training_days, region, download_path):
base_url = f"https://data.binance.vision/data/spot/daily/klines"
end_date = date.today()
start_date = end_date - timedelta(days=int(training_days))
response = requests.get(url)
if response.status_code == 404:
# print(f"File not exist: {url}")
pass
global files
files = []
with ThreadPoolExecutor() as executor:
print(f"Downloading data for {pair}")
for single_date in daterange(start_date, end_date):
url = f"{base_url}/{pair}/1m/{pair}-1m-{single_date}.zip"
executor.submit(download_url, url, download_path)
return files
def download_binance_current_day_data(pair, region):
limit = 1000
base_url = f'https://api.binance.{region}/api/v3/klines?symbol={pair}&interval=1m&limit={limit}'
# Make a request using the session object
response = session.get(base_url)
response.raise_for_status()
resp = str(response.content, 'utf-8').rstrip()
columns = ['start_time','open','high','low','close','volume','end_time','volume_usd','n_trades','taker_volume','taker_volume_usd','ignore']
df = pd.DataFrame(json.loads(resp),columns=columns)
df['date'] = [pd.to_datetime(x+1,unit='ms') for x in df['end_time']]
df['date'] = df['date'].apply(pd.to_datetime)
df[["volume", "taker_volume", "open", "high", "low", "close"]] = df[["volume", "taker_volume", "open", "high", "low", "close"]].apply(pd.to_numeric)
return df.sort_index()
def get_coingecko_coin_id(token):
token_map = {
'ETH': 'ethereum',
'SOL': 'solana',
'BTC': 'bitcoin',
'BNB': 'binancecoin',
'ARB': 'arbitrum',
# Add more tokens here
}
token = token.upper()
if token in token_map:
return token_map[token]
else:
# create the entire path if it doesn't exist
os.makedirs(os.path.dirname(target_file_path), exist_ok=True)
with open(target_file_path, "wb") as f:
f.write(response.content)
# print(f"Downloaded: {url} to {target_file_path}")
raise ValueError("Unsupported token")
def download_binance_monthly_data(
cm_or_um, symbols, intervals, years, months, download_path
):
# Verify if CM_OR_UM is correct, if not, exit
if cm_or_um not in ["cm", "um"]:
print("CM_OR_UM can be only cm or um")
return
base_url = f"https://data.binance.vision/data/futures/{cm_or_um}/monthly/klines"
def download_coingecko_data(token, training_days, download_path, CG_API_KEY):
if training_days <= 7:
days = 7
elif training_days <= 14:
days = 14
elif training_days <= 30:
days = 30
elif training_days <= 90:
days = 90
elif training_days <= 180:
days = 180
elif training_days <= 365:
days = 365
else:
days = "max"
print(f"Days: {days}")
# Main loop to iterate over all the arrays and launch child processes
with ThreadPoolExecutor() as executor:
for symbol in symbols:
for interval in intervals:
for year in years:
for month in months:
url = f"{base_url}/{symbol}/{interval}/{symbol}-{interval}-{year}-{month}.zip"
executor.submit(download_url, url, download_path)
coin_id = get_coingecko_coin_id(token)
print(f"Coin ID: {coin_id}")
# Get OHLC data from Coingecko
url = f'https://api.coingecko.com/api/v3/coins/{coin_id}/ohlc?vs_currency=usd&days={days}&api_key={CG_API_KEY}'
def download_binance_daily_data(
cm_or_um, symbols, intervals, year, month, download_path
):
if cm_or_um not in ["cm", "um"]:
print("CM_OR_UM can be only cm or um")
return
base_url = f"https://data.binance.vision/data/futures/{cm_or_um}/daily/klines"
global files
files = []
with ThreadPoolExecutor() as executor:
for symbol in symbols:
for interval in intervals:
for day in range(1, 32): # Assuming days range from 1 to 31
url = f"{base_url}/{symbol}/{interval}/{symbol}-{interval}-{year}-{month:02d}-{day:02d}.zip"
executor.submit(download_url, url, download_path)
print(f"Downloading data for {coin_id}")
name = os.path.basename(url).split("?")[0].replace("/", "_") + ".json"
executor.submit(download_url, url, download_path, name)
return files
def download_coingecko_current_day_data(token, CG_API_KEY):
coin_id = get_coingecko_coin_id(token)
print(f"Coin ID: {coin_id}")
url = f'https://api.coingecko.com/api/v3/coins/{coin_id}/ohlc?vs_currency=usd&days=1&api_key={CG_API_KEY}'
# Make a request using the session object
response = session.get(url)
response.raise_for_status()
resp = str(response.content, 'utf-8').rstrip()
columns = ['timestamp','open','high','low','close']
df = pd.DataFrame(json.loads(resp), columns=columns)
df['date'] = [pd.to_datetime(x,unit='ms') for x in df['timestamp']]
df['date'] = df['date'].apply(pd.to_datetime)
df[["open", "high", "low", "close"]] = df[["open", "high", "low", "close"]].apply(pd.to_numeric)
return df.sort_index()